Presence-only data

library(plotly)
library(packcircles)
library(ggiraph)
library(countrycode)
library(tmap)
tmap_mode('view')
library(sf)
sf::sf_use_s2(FALSE)
library(tidyverse)

Data

List of species

carnivores <- read_csv('data/carnivores.csv')

Number of carnivore species in the Neotropics = 71

Countries

countries <- st_read('data/latam.gpkg', layer = 'countries', quiet = T)

Number of countries in the Neotropics = 21

Presence only records

PO <- read_csv('data/data_PO.csv')

data_PO <- PO %>% 
  st_as_sf(coords=c('decimalLongitude', 'decimalLatitude')) %>%
  st_set_crs(4326)

Number of PO records = 60179
Number of species represented in the PO data = 60 (84.5 %)

Sources

Top 10 data publishers (institutions)

data_PO %>% st_drop_geometry() %>% 
  count(institutionCode) %>% 
  arrange(desc(n)) %>% filter(!is.na(institutionCode)) %>% 
  slice_head(n=10) %>% 
  mutate(`%` = formattable::percent(n / sum(n))) %>% 
  kableExtra::kbl()

institutionCode	n	%
iNaturalist	19439	47.08%
Corporación Nacional Forestal (CONAF)	8031	19.45%
APN-AR	2779	6.73%
MMA:GEFMONT	1871	4.53%
Asociación Colombiana de Zoología (ACZ)	1849	4.48%
Ecopetrol S.A.	1816	4.40%
MAATE	1467	3.55%
IBUNAM	1438	3.48%
Parques Nacionales Naturales de Colombia (PNN)	1320	3.20%
Instituto de Investigación de Recursos Biológicos Alexander von Humboldt (IAvH)	1277	3.09%

Number of datasets involved in the PO data = 434

Geographic coverage

tmap_mode('plot')
tm_shape(data_PO) +
    tm_dots(col='year', size = 0.1, palette= 'Greys') + 
    tm_facets(by = 'countryCode' ) +
    tm_shape(countries) +
    tm_borders(col='grey60', alpha = 0.5) +
    tm_layout(asp = 0, legend.outside= T, legend.outside.size = 0.1)

data_PO %>% 
  st_drop_geometry() %>% 
  mutate(Country=countrycode(countryCode,
                             origin = 'iso2c', 
                             destination = 'country.name')) %>%
  group_by(Country) %>%
  summarise(`Number of records`=n(), 
            `Number of species`=n_distinct(scientificName)) %>% 
  mutate(code=countrycode(Country,
                             origin = 'country.name', 
                             destination = 'iso2c')) %>%
  relocate(Country, code) %>% 
  kableExtra::kbl()

Country	code	Number of records	Number of species
Argentina	AR	4828	24
Belize	BZ	215	14
Bolivia	BO	145	19
Brazil	BR	5356	26
Chile	CL	10632	11
Colombia	CO	12780	31
Costa Rica	CR	3029	21
Ecuador	EC	2922	27
El Salvador	SV	55	10
French Guiana	GF	1172	15
Guatemala	GT	309	16
Guyana	GY	29	14
Honduras	HN	121	14
Mexico	MX	15409	29
Nicaragua	NI	47	13
Panama	PA	428	16
Paraguay	PY	782	16
Peru	PE	747	21
Suriname	SR	953	11
Uruguay	UY	189	7
Venezuela	VE	31	11

Number of countries represented in the PO data = 21

Taxonomic coverage

data <- data_PO %>% st_drop_geometry() %>% 
  group_by(family) %>% 
  summarise(n_records=n(), n_species=n_distinct(scientificName)) 

packing <- circleProgressiveLayout(data$n_records, sizetype='area')
data <- cbind(data, packing)
packing$radius <- 0.95*packing$radius

dat.gg <- circleLayoutVertices(packing, npoints=50)
data$text <- paste("family: ", data$family, 
                   "\n", "records:", data$n_records, 
                   "\n", "species:", data$n_species)

plot.gg <- ggplot() + 
  geom_polygon_interactive(data = dat.gg,
                           aes(x, y, group = id, fill=id,
                               tooltip = data$text[id],
                               data_id = id), colour = "black", alpha = 0.6) +
  scale_fill_continuous_interactive(type = 'viridis') +
  geom_text(data = data, aes(x, y, label = gsub("Group_", "", family)), size=3, color="black") +
  theme_void() + 
  theme(legend.position="none", plot.margin=unit(c(0,0,0,0),"cm") ) + 
  coord_equal()

x <- girafe(ggobj = plot.gg)
x

data_PO %>% st_drop_geometry() %>% 
  group_by(scientificName, family) %>% count %>% 
  arrange(family, scientificName, n) %>% 
  rename(`Number of records`=n) %>% 
  kableExtra::kbl()

scientificName	family	Number of records
Atelocynus microtis	Canidae	41
Canis latrans	Canidae	2288
Canis lupus	Canidae	241
Cerdocyon thous	Canidae	4332
Chrysocyon brachyurus	Canidae	575
Lycalopex culpaeus	Canidae	8561
Lycalopex fulvipes	Canidae	72
Lycalopex grisea	Canidae	80
Lycalopex gymnocerca	Canidae	2087
Lycalopex sechurae	Canidae	13
Lycalopex vetula	Canidae	91
Speothos venaticus	Canidae	60
Urocyon cinereoargenteus	Canidae	2868
Vulpes macrotis	Canidae	132
Herpailurus yagouaroundi	Felidae	1171
Leopardus colocola	Felidae	183
Leopardus geoffroyi	Felidae	302
Leopardus guigna	Felidae	509
Leopardus guttulus	Felidae	34
Leopardus jacobitus	Felidae	1
Leopardus pajeros	Felidae	8
Leopardus pardalis	Felidae	3371
Leopardus tigrinus	Felidae	379
Leopardus wiedii	Felidae	471
Lynx rufus	Felidae	1055
Panthera onca	Felidae	1230
Puma concolor	Felidae	3999
Conepatus chinga	Mephitidae	629
Conepatus leuconotus	Mephitidae	406
Conepatus semistriatus	Mephitidae	578
Mephitis macroura	Mephitidae	569
Mephitis mephitis	Mephitidae	210
Spilogale angustifrons	Mephitidae	161
Spilogale gracilis	Mephitidae	106
Spilogale pygmaea	Mephitidae	16
Eira barbara	Mustelidae	2957
Galictis cuja	Mustelidae	374
Galictis vittata	Mustelidae	196
Lontra canadensis	Mustelidae	1
Lontra longicaudis	Mustelidae	959
Lontra provocax	Mustelidae	81
Neogale felipei	Mustelidae	1
Neogale frenata	Mustelidae	251
Pteronura brasiliensis	Mustelidae	272
Taxidea taxus	Mustelidae	154
Bassaricyon alleni	Procyonidae	32
Bassaricyon gabbii	Procyonidae	53
Bassaricyon medius	Procyonidae	11
Bassaricyon neblina	Procyonidae	26
Bassariscus astutus	Procyonidae	1113
Bassariscus sumichrasti	Procyonidae	63
Nasua narica	Procyonidae	5127
Nasua nasua	Procyonidae	2620
Nasua olivacea	Procyonidae	275
Potos flavus	Procyonidae	815
Procyon cancrivorus	Procyonidae	2681
Procyon lotor	Procyonidae	2098
Procyon pygmaeus	Procyonidae	1
Tremarctos ornatus	Ursidae	2753
Ursus americanus	Ursidae	436

Species not covered

# species not included  
carnivores %>% 
  filter(!species %in% unique(data_PO$scientificName)) %>%
  select(species, family) %>%  arrange(family, species) %>% 
  kableExtra::kbl()

species	family
Leopardus braccatus	Felidae
Leopardus emiliae	Felidae
Leopardus fasciatus	Felidae
Leopardus garleppi	Felidae
Leopardus jacobita	Felidae
Leopardus narinensis	Felidae
Spilogale interrupta	Mephitidae
Spilogale leucoparia	Mephitidae
Spilogale yucatanensis	Mephitidae
Enhydra lutris	Mustelidae
Lyncodon patagonicus	Mustelidae
Neogale africana	Mustelidae

Temporal coverage

coef <- 150

plot_records <- data_PO %>% st_drop_geometry() %>% 
  mutate(date_observed = dmy(str_c(day, month, year, sep='-'))) %>% 
  add_count(year, name='records_per_year') %>% 
  group_by(year) %>% 
  mutate(species_per_year= n_distinct(scientificName)) %>% ungroup() %>% 
    ggplot(aes(x=date_observed)) +
    geom_line(aes(y=records_per_year, col='Records'), 
              linewidth=1, col=RColorBrewer::brewer.pal(9, 'Set1')[2]) +
    scale_y_continuous(n.breaks = 10) +
    scale_x_date(date_breaks = "2 years", date_labels = "%Y") +
    theme_bw() + labs(x='',, y='Number of records', col='')

plot_species <- data_PO %>% st_drop_geometry() %>% 
  mutate(date_observed = dmy(str_c(day, month, year, sep='-'))) %>% 
  add_count(year, name='records_per_year') %>% 
  group_by(year) %>% mutate(species_per_year= n_distinct(scientificName)) %>% ungroup() %>% 
  ggplot(aes(x=date_observed)) +
  geom_line(aes(y=species_per_year, col='species'), linewidth=1, 
            col=RColorBrewer::brewer.pal(9, 'Set1')[1]) +
  scale_x_date(date_breaks = "2 years", date_labels = "%Y") +
  theme_bw() + labs(x='',, y='Number of species', col='')

plot_records <- ggplotly(plot_records)
plot_records

plot_species <- ggplotly(plot_species)
plot_species